Skip to yearly menu bar Skip to main content


( events)   Timezone:  
Workshop
Fri Jul 28 12:00 PM -- 08:00 PM (PDT) @ Meeting Room 323 None
Structured Probabilistic Inference and Generative Modeling
Dinghuai Zhang · Yuanqi Du · Chenlin Meng · Shawn Tan · Yingzhen Li · Max Welling · Yoshua Bengio





Workshop Home Page

The workshop focuses on theory, methodology, and application of structured probabilistic inference and generative modeling, both of which are important topics in machine learning.Specifically, probabilistic inference addresses the problem of amortization,sampling, and integration of complex quantities from graphical models, while generative modeling captures the underlying probability distributions of a dataset. Apart from applications in computer vision, natural language processing, and speech recognition, probabilistic inference and generative modeling approaches have also been widely used in natural science domains, including physics, chemistry, molecular biology, and medicine. Despite the promising results, probabilistic methods face challenges when applied to highly structured data, which are ubiquitous in real-world settings, limiting the applications of such methods. This workshop aims to bring experts from diverse backgrounds and related domains together to discuss the applications and challenges of probabilistic methods. The workshop will emphasize challenges in encoding domain knowledge when learning representations, performing inference and generations. By bringing together experts from academia and industry, the workshop will provide a platform for researchers to share their latest results and ideas, fostering collaboration and discussion in the field of probabilistic methods.

Opening Remark
Invited Talk by Karen Ullrich (Invited Talk)
Invited Talk by Tommi Jaakkola (Invited Talk)
Coffee Break (Break)
Invited Talk by Durk Kingma (Invited Talk)
Collapsed Inference for Bayesian Deep Learning (Contributed Talk)
Provable benefits of score matching (Contributed Talk)
Poster Session 1 (Poster Session)
Panel Discussion
Invited Talk by Ruqi Zhang (Invited Talk)
Invited Talk by Stefano Ermon (Invited Talk)
BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery (Contributed Talk)
Generative Marginalization Models (Contributed Talk)
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network (Contributed Talk)
Closing Remark
Poster Session 2 (Poster Session)
Function Space Bayesian Pseudocoreset for Bayesian Neural Networks (Poster)
Structured Neural Networks for Density Estimation (Poster)
An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets (Poster)
Augmenting Control over Exploration Space in Molecular Dynamics Simulators to Streamline De Novo Analysis through Generative Control Policies (Poster)
An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (Poster)
Diffusion Generative Inverse Design (Poster)
Early Exiting for Accelerated Inference in Diffusion Models (Poster)
Prediction under Latent Subgroup Shifts with High-dimensional Observations (Poster)
BayesDAG: Gradient-Based Posterior Sampling for Causal Discovery (Oral)
HiGen: Hierarchical Graph Generative Networks (Poster)
Morse Neural Networks for Uncertainty Quantification (Poster)
Large Dimensional Change Point Detection with FWER Control as Automatic Stopping (Poster)
Nested Diffusion Processes for Anytime Image Generation (Poster)
GSURE-Based Diffusion Model Training with Corrupted Data (Poster)
Causal Discovery with Language Models as Imperfect Experts (Poster)
Balanced Training of Energy-Based Models with Adaptive Flow Sampling (Poster)
GFlowNets for Causal Discovery: an Overview (Poster)
STable Permutation-based Framework for Table Generation in Sequence-to-Sequence Models (Poster)
Visual Chain-of-Thought Diffusion Models (Poster)
Scaling Graphically Structured Diffusion Models (Poster)
Collapsed Inference for Bayesian Deep Learning (Oral)
DiffMol: 3D Structured Molecule Generation with Discrete Denoising Diffusion Probabilistic Models (Poster)
AbODE: Ab initio antibody design using conjoined ODEs (Poster)
Robust and Scalable Bayesian Online Changepoint Detection (Poster)
Neuro-Causal Factor Analysis (Poster)
On the Identifiability of Markov Switching Models (Poster)
Fit Like You Sample: Sample-Efficient Generalized Score Matching from Fast Mixing Markov Chains (Poster)
Provable benefits of score matching (Oral)
Attention as Implicit Structural Inference (Poster)
Identifiability of Discretized Latent Coordinate Systems via Density Landmarks Detection (Poster)
Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network (Oral)
A Generative Model for Text Control in Minecraft (Poster)
Thompson Sampling for Improved Exploration in GFlowNets (Poster)
Improving Training of Likelihood-based Generative Models with Gaussian Homotopy (Poster)
Optimizing protein fitness using Bi-level Gibbs sampling with Graph-based Smoothing (Poster)
Dimensionality Reduction as Probabilistic Inference (Poster)
Inferring Hierarchical Structure in Multi-Room Maze Environments (Poster)
Multilevel Control Functional (Poster)
Generative Marginalization Models (Oral)
Benchmarking Bayesian Causal Discovery Methods for Downstream Treatment Effect Estimation (Poster)
BatchGFN: Generative Flow Networks for Batch Active Learning (Poster)
Towards Modular Learning of Deep Causal Generative Models (Poster)
Diffusion map particle systems for generative modeling (Poster)
Nonparametric posterior normalizing flows (Poster)
CM-GAN: Stabilizing GAN Training with Consistency Models (Poster)
Learning Linear Causal Representations from Interventions under General Nonlinear Mixing (Poster)
Generative semi-supervised learning with a neural seq2seq noisy channel (Poster)
Conditional Graph Generation with Graph Principal Flow Network (Poster)
Deep Generative Clustering with Multimodal Variational Autoencoders (Poster)
Plug-and-Play Controllable Graph Generation with Diffusion Models (Poster)
Pretrained Language Models to Solve Graph Tasks in Natural Language (Poster)
Non-Normal Diffusion Models (Poster)
Beyond Confidence: Reliable Models Should Also Consider Atypicality (Poster)
Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models (Poster)
Solving Inverse Physics Problems with Score Matching (Poster)
Diffusion Based Causal Representation Learning (Poster)
Training Diffusion Models with Reinforcement Learning (Poster)
Generating Turn-Based Player Behavior via Experience from Demonstrations (Poster)
Automatic Rao-Blackwellization for Sequential Monte Carlo with Belief Propagation (Poster)
Exploring Exchangeable Dataset Amortization for Bayesian Posterior Inference (Poster)
Identifying Under-Reported Events in Networks with Spatial Latent Variable Models (Poster)
Variational Point Encoding Deformation for Dental Modeling (Poster)
Autoregressive Diffusion Models with non-Uniform Generation Order (Poster)
Diffusion Probabilistic Models for Structured Node Classification (Poster)
Score-based Enhanced Sampling for Protein Molecular Dynamics (Poster)
Reinforcement Learning-Driven Linker Design via Fast Attention-based Point Cloud Alignment (Poster)
Parallel Sampling of Diffusion Models (Poster)
Regularized Data Programming with Automated Bayesian Prior Selection (Poster)
Concept Algebra for Score-based Conditional Model (Poster)
Your Diffusion Model is Secretly a Zero-Shot Classifier (Poster)
Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences (Poster)
Collaborative Score Distillation for Consistent Visual Synthesis (Poster)
Practical and Asymptotically Exact Conditional Sampling in Diffusion Models (Poster)
Hierarchical Graph Generation with $K^{2}$-trees (Poster)
Fast and Functional structured data generator (Poster)
The Local Inconsistency Resolution Algorithm (Poster)
The Pairwise Prony Algorithm: Efficient Inference of Stochastic Block Models with Prescribed Subgraph Densities (Poster)
Test-time Adaptation with Diffusion Models (Poster)
Tree Variational Autoencoders (Poster)
PRODIGY: Enabling In-context Learning Over Graphs (Poster)
Graph Neural Network Powered Bayesian Optimization for Large Molecular Spaces (Poster)
Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Data (Poster)
Diffusion Probabilistic Models Generalize when They Fail to Memorize (Poster)
Implications of kernel mismatch for OOD data (Poster)
MissDiff: Training Diffusion Models on Tabular Data with Missing Values (Poster)
Uncovering Latent Structure Using Random Partition Models (Poster)
Geometric Constraints in Probabilistic Manifolds: A Bridge from Molecular Dynamics to Structured Diffusion Processes (Poster)
C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder (Poster)
Diffusion Models with Grouped Latents for Interpretable Latent Space (Poster)
PITS: Variational Pitch Inference Without Fundamental Frequency for End-to-End Pitch-Controllable TTS (Poster)
Beyond Intuition, a Framework for Applying GPs to Real-World Data (Poster)
HINT: Hierarchical Coherent Networks For Constrained Probabilistic Forecasting (Poster)
On the Equivalence of Consistency-Type Models: Consistency Models, Consistent Diffusion Models, and Fokker-Planck Regularization (Poster)
Anomaly Detection in Networks via Score-Based Generative Models (Poster)
Flow Matching for Scalable Simulation-Based Inference (Poster)
Lexinvariant Language Models (Poster)